• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.9
• /
• pp.2129-2137
• /
• 2015

Lots of research and development works have been actively focused on the self-driving vehicles, locally and globally. In order to implement the self-driving vehicles, lots of fundamental core technologies need to be successfully developed and, specially, it is noted that traffic lights detection and recognition system is an essential part of the computer vision technologies in the self-driving vehicles. Up to nowadays, most conventional algorithm for detecting and recognizing traffic lights are mainly based on the color signal analysis, but these approaches have limits on the performance improvements that can be achieved due to the color signal noises and environmental situations. In order to overcome the performance limits, this paper introduces the morphological analysis for the traffic lights recognition. That is, by considering the color component analysis and the shape analysis such as rectangles and circles simultaneously, the efficiency of the traffic lights recognitions can be greatly increased. Through several simulations, it is shown that the proposed method can highly improve the recognition rate as well as the mis-recognition rate.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.3
• /
• pp.1519-1526
• /
• 2013

This study reviewed the capturing performance of a canopy hood used in some melting processes of a casting manufacturing factory through a site survey. In addition, this study compared and evaluated the flow field and pressure field for the plans to enhance the hazardous air pollutants collection capacity by using CFD model. The case-2(flange attached + double hood) can be improved in terms of collection performance, but is expected to increase in hood static pressure by about 70% more than the existing structure, so it was shown that its site applicability is not good. It is judged that the shape of case-3(flange attached + double cone attached) is most suitable to improve the suction efficiency. This is because a double cone is installed at the center of the opening to concentrate the flow rate on the edge of the hood and control the hume rising to the center of the hood without a static pressure rise via the slope of the cone.

• Journal of Internet of Things and Convergence
• /
• v.9 no.1
• /
• pp.131-138
• /
• 2023

This paper is related to performance improvement of Image-to-Image translation using Relativistic Average Patch GAN and Residual in Residual Dense Block. The purpose of this paper is to improve performance through technical improvements in three aspects to compensate for the shortcomings of the previous pix2pix, a type of Image-to-Image translation. First, unlike the previous pix2pix constructor, it enables deeper learning by using Residual in Residual Block in the part of encoding the input image. Second, since we use a loss function based on Relativistic Average Patch GAN to predict how real the original image is compared to the generated image, both of these images affect adversarial generative learning. Finally, the generator is pre-trained to prevent the discriminator from being learned prematurely. According to the proposed method, it was possible to generate images superior to the previous pix2pix by more than 13% on average at the aspect of FID.

• Journal of Convergence Society for SMB
• /
• v.6 no.4
• /
• pp.93-98
• /
• 2016

Recently, the project related to the smart grid are being actively studied around the developed world. In particular, the long-term stabilization measures distributed power supply problem has been highlighted. In this paper, we propose a three-dimensional numerical weather prediction models to compare the error rate information which combined with the physical models and statistical models to predict the output of distributed power. Proposed model can predict the system for a stable power grid-can improve the prediction information of the distributed power. In performance evaluation, proposed model was a generation forecasting accuracy improved by 4.6%, temperature compensated prediction accuracy was improved by 3.5%. Finally, the solar radiation correction accuracy is improved by 1.1%.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2008.04a
• /
• pp.933-936
• /
• 2008

An engineered cementitious composite (Engineered Cementitious Composite) had been developed in previous study. Theoretical prediction of the tensile stress-strain relation of ECC is important in providing the material constitutive relation necessary for designing structural members. But, few studies have been reported with regard to predicting the tensile stress-strain relation of ECC. Prediction of the tensile stress-strain relation of ECC accounting for actual bridging curve, such as fiber dispersion is needed. The present study extends the work as developed by Kanda et al., by modeling the bridging curve, accounting for fiber dispersion, the degree of matrix spalling, and fiber rupture to predict the tensile stress-strain relation of ECC. The role of material variation in the bridging curve, such as number of effective fiber actually involved in the bridging capacity and how it affects the multiple cracking process is discussed. The approach for formulating the tensile stress-strain relation is discussed next, where the procedure for obtaining the necessary parameters, such as the crack spacing, is presented. Finally, the predicted stress-strain relation will be validated with experimental tests results.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 1998.04a
• /
• pp.10-10
• /
• 1998

본 연구에서는 제트 추진 기관의 터빈 익렬에서의 유동과 대기 중에 부유되어 있는 입자 또는 연소 생성물들이 제트엔진 내부로 유입될 경우 이에 따른 압축기 및 터빈 날개의 마모 및 충돌 부위를 예측하기 위하여 수치해석을 수행하였다. 일반적으로 각종 항공기의 추진 기관용 가스 터빈 엔진은 대기중에 부유되어 있는 각종 입자들의 영향을 받게 된다. 특히, 확산 지역을 통과하는 항공기나 먼지 입자 부유물이 많은 공업지대 또는 사막지역을 비행하는 항공기의 경우는 모래 알갱이, 먼지 및 연소 입자의 직접적인 영향을 받아 각 요소들에 심각한 부식 및 마모가 발생됨으로써 성능 저하 및 냉각 통로의 막힘, 압축기와 터빈 날개의 손상 등이 예측되어진다. 특히 항공기용 추진 기관은 엔진 입구에 유입 공기를 정화하기 위한 여과장치의 설치가 불가능하며, 자동차용 가스터빈 엔진의 경우는 여과 장치를 부착하여도 미세한 입자들이 여과 장치에 여과되지 않고 엔진 내부로 침투하게 되므로 치명적인 손상이 예상된다. 이러한 손상들은 초기에는 미세하게 발생하지만, 손상 정도가 점점 누적됨에 따라서 항공기의 안전 운전에 심각한 위험 요소로서 작용할 수 있으며, 경제적으로도 기관의 유지 보수비용의 증가를 가져올 수 있다. 따라서 압축기에 화산재 또는 대기중에 부유되어 있는 금속 입자나 먼지입자 등이 유입되었을 경우, 압축기 날개의 손상 부위와 정도를 예측하는 것이 필요하다. 따라서 본 연구에서는 Lagangian방법을 적용하여 압축기 날개위의 부유 입자 충돌 부위를 예측하고, 설계 시 이를 보완할 수 있는 기준을 제시하였다. 아울러 설계 입구각과 크게 벗어난 유동의 유입시에 발생되는 박리 현상과 이에 따른 입자의 유동 및 날개의 입자 접착 부위를 예측하였다. 본 연구에서는 여러 크기의 입자(다양한 Stokes 수)들을 주어진 속도에서 유선을 따라 압축기 입구에서 압축기 유로로 여러 위치에서 부유 시켜서 그 입자들의 궤적 및 충돌, 점착 위지를 고찰하고, 정량적인 충돌량을 해석하기 위하여 입자 충돌 계수를 정의하여 압축기 날개 표면의 충돌특성을 알아보았다. 이러한 예측을 통하여 압축기 날개 표면의 충돌 부위를 예측하고, 날개의 표면을 코팅하는 등 보호 개선책을 제시할 수 있고, 연소의 반응물 입자가 터빈 날개에 충돌하여 발생되는 날개 표면의 파손, 냉각 홀의 막임, 연소 입자의 점착 부위 등을 예측하여 보완책을 준비할 수 있도록 하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.945-949
• /
• 2009

This paper proposes an enhanced motion estimation that is one of core parts affecting the coding performance and visual quality in video coding. Although the full search technique, which is the most basic method of the motion estimation, presents the best visual quality, its computational complexity is great, since the search procedures to find the best matched block with each block in the current frame are carried out for all points inside the search area. Thus, various fast algorithms to reduce the computational complexity and maintain good visual quality have been proposed. The PMVFAST adopted the MPEG-4 visual standard produces the visual quality near that by the full search technique with the reduced computational complexity. In this paper, we propose a new motion vector prediction method using median processing. The proposed method reduces the computational complexity for the motion estimation significantly. Experimental results show that the proposed algorithm is faster than the PMVFAST and better than the full search in terms of search speed and average PSNR, respectively.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.381-381
• /
• 2020

자료동화(Data Assimilation) 기법은 실시간 수문학적 예측에 있어 정확도 향상을 위해 필수적인 과정이다. 가장 대중적으로 사용되는 기법들 중 하나가 모델 상태변수와 매개변수를 동시에 업데이트할 수 있는 이중 앙상블 칼만 필터(Dual Ensemble Kalman Filter)이다. 이 방법은 정확도 개선 및 적용의 용이성 때문에 많은 연구 분야에서 사용되어져 왔지만, 앙상블을 생성하는 과정에서 상당시간이 소요되는 단점이 존재한다. 본 연구에서는 상태변수와 매개변수를 동시에 업데이트 하면서 홍수 예측의 정확성을 보장할 뿐만 아니라, 앙상블 생성에 있어 계산 효율을 크게 향상시킬 수 있는 기법을 제안한다. Polynomial Chaos Expansion(PCE) 기법을 사용하여 앙상블 칼만 필터를 모방(mimic)할 수 있는 새로운 대체필터(Surrogate Filter)를 개발하는 것을 목표로 한다. 구체적으로 대체필터를 구성하기 위한 다양한 필터를 설계하였다. 첫째 시간에 대해서 PCE가 변화하지 않는 '불변 필터'(즉, 전체 예측기간에 대해 하나의 필터를 사용하여 자료동화할 수 있는 대체필터)와, 매 시간마다 PCE가 변화하는 '시변 필터'(즉, 예측하는 매 시간마다 새로운 필터를 생성해야 하는 대체필터)를 설계하여 적용성, 정확성, 예측성 등을 비교하였다. 또한, PCE의 하이퍼 매개변수를 최적화하기 위한 최적의 프레임 워크가 제안되어, 대체필터를 구축하는 데 효율을 높이고 PCE의 과적합(overfitting) 현상을 피할 수 있도록 하였다. 본 연구에서 제안된 기법은 기존 단일 및 이중 앙상블 칼만 필터(EnKF)의 결과와 비교 검증하였으며, 그 결과는 다음과 같다. (1) 대체필터의 대부분은 원래 EnKF와 비슷한 정도의 불확실성을 설명할 수 있음; (2) 모든 대체 필터는 선행시간이 짧은 경우의 예측에 있어 우수한 결과를 제공하며, 시변 필터가 불변 필터보다 더 정확한 예측 결과를 제공함; (3) 대체필터는 원래 앙상블 칼만필터보다 최대 500배 빠른 속도로 성능을 향상시킬 수 있음. 제안된 대체필터는 자료동화를 수행하는 기존필터와 비슷한 정도의 정확성, 매우 향상된 효율성을 보장함을 확인할 수 있었다.

• The Journal of Engineering Geology
• /
• v.32 no.4
• /
• pp.697-723
• /
• 2022

Data-driven models to predict groundwater levels 30 days in advance were developed for 12 groundwater monitoring stations in the middle-Jeju watershed, Jeju Island. Stacked long short-term memory (stacked-LSTM), a deep learning technique suitable for time series forecasting, was used for model development. Daily time series data from 2001 to 2022 for precipitation, groundwater usage amount, and groundwater level were considered. Various models were proposed that used different combinations of the input data types and varying lengths of previous time series data for each input variable. A general procedure for deep-learning-based model development is suggested based on consideration of the comparative validation results of the tested models. A model using precipitation, groundwater usage amount, and previous groundwater level data as input variables outperformed any model neglecting one or more of these data categories. Using extended sequences of these past data improved the predictions, possibly owing to the long delay time between precipitation and groundwater recharge, which results from the deep groundwater level in Jeju Island. However, limiting the range of considered groundwater usage data that significantly affected the groundwater level fluctuation (rather than using all the groundwater usage data) improved the performance of the predictive model. The developed models can predict the future groundwater level based on the current amount of precipitation and groundwater use. Therefore, the models provide information on the soundness of the aquifer system, which will help to prepare management plans to maintain appropriate groundwater quantities.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.6
• /
• pp.571-576
• /
• 2002

There have been a lot of considerations dealing with improving the performance of neuro-fuzzy system. The studies on the neuro-fuzzy modeling have largely been devoted to two approaches. First is to improve performance index of system. The other is to reduce the structure size. In spite of its satisfactory result, it should be noted that these are difficult to extend to high dimensional input or to increase the membership functions. We propose a novel neuro-fuzzy system based on the efficient clustering method for initializing the parameters of the premise part. It is a very useful method that maintains a few number of rules and improves the performance. It combine the various algorithms to improve the performance. The Expectation-Maximization algorithm of Gaussian mixture model is an efficient estimation method for unknown parameter estimation of mirture model. The obtained parameters are used for fuzzy clustering method. The proposed method satisfies these two requirements using the Gaussian mixture model and neuro-fuzzy modeling. Experimental results indicate that the proposed method is capable of giving reliable performance.